Giskard Headlines

Giskard Blog

Giskard launched Phare, a new open and independent LLM benchmark to evaluate AI security dimensions like hallucination, factual accuracy, bias, and potential for harm across multiple languages, with Google DeepMind as a research partner. This initiative aims to provide open measurements for assessing the trustworthiness of Generative AI models in real applications.

Companies:Giskard

TechCrunch

Giskard offers an open-source framework that helps data scientists and ML engineers evaluate AI models for potential issues like bias, performance, and security vulnerabilities before deployment. This helps ensure responsible AI development and prevents problematic models from reaching production.

Companies:Giskard

Giskard Blog

Giskard secured $1.5 million in funding to further develop its platform, which assists data scientists in identifying and resolving vulnerabilities within AI models. This investment will accelerate their mission to ensure the reliability and safety of AI systems.

Companies:Giskard